CN113655786B - Unmanned boat group control method based on African bee intelligent algorithm - Google Patents
Unmanned boat group control method based on African bee intelligent algorithm Download PDFInfo
- Publication number
- CN113655786B CN113655786B CN202110722765.6A CN202110722765A CN113655786B CN 113655786 B CN113655786 B CN 113655786B CN 202110722765 A CN202110722765 A CN 202110722765A CN 113655786 B CN113655786 B CN 113655786B
- Authority
- CN
- China
- Prior art keywords
- grid
- sea area
- speed
- sea
- unmanned
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 241000392905 Apis mellifera adansonii Species 0.000 title claims abstract description 11
- 239000011159 matrix material Substances 0.000 claims abstract description 47
- 238000012937 correction Methods 0.000 claims abstract description 37
- 230000008569 process Effects 0.000 abstract description 16
- 238000004891 communication Methods 0.000 description 18
- 238000001514 detection method Methods 0.000 description 9
- 239000003016 pheromone Substances 0.000 description 9
- 238000012360 testing method Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 241000256844 Apis mellifera Species 0.000 description 2
- 241000257303 Hymenoptera Species 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 241000283153 Cetacea Species 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/0206—Control of position or course in two dimensions specially adapted to water vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING
- B63B79/00—Monitoring properties or operating parameters of vessels in operation
- B63B79/40—Monitoring properties or operating parameters of vessels in operation for controlling the operation of vessels, e.g. monitoring their speed, routing or maintenance schedules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Radar, Positioning & Navigation (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Remote Sensing (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Aviation & Aerospace Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Ocean & Marine Engineering (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The application discloses an unmanned boat group control method based on an African bee intelligent algorithm, which comprises the following steps: based on the unmanned ship group operation task and the African peak algorithm, adopting iterative operation, and determining the initial navigational speed and the predicted navigational position of the unmanned ship single ship according to the current position and the current navigational speed of the unmanned ship single ship in the operation sea area; gridding the operation sea area according to sea state information of the operation sea area, generating operation task grids, and determining a task grid information matrix of the operation task grids; determining a sub-grid of the operation task grid corresponding to the predicted sailing position, determining a sailing speed correction amount according to the sub-grid to correct the initial sailing speed, and generating a control instruction according to the corrected initial sailing speed and the predicted sailing position to control the unmanned boat to sail to the sub-grid until the unmanned boat group operation task is completed. According to the technical scheme, the navigational speed and the navigational direction of the unmanned ship in the navigational process are optimized, and the cooperative control of the unmanned ship group is performed in real time.
Description
Technical Field
The application relates to the technical field of unmanned boats, in particular to an unmanned boat group control method based on an African bee intelligent algorithm.
Background
With development and exploration of ocean, unmanned ships are increasingly gaining attention as an on-water intelligent device in various countries, and are developed world by world, and the development is very rapid, especially the breakthrough and application of key technologies such as intellectualization and the like, or the sea warfare form in the future military field is changed. Unmanned boats are continuously applied and developed in a plurality of army and civil fields such as ocean patrol, search and rescue, combat, ocean environment detection and the like by virtue of the excellent advantages.
The unmanned ship has the functions of remote control and autonomous navigation, is especially suitable for the operation tasks of complex environments such as operation by persons in severe sea conditions, and has the advantages of cluster effect for unmanned ship groups, small unmanned ship course, high navigational speed, strong adaptability, high safety and high efficiency and low cost for large-area operation under unknown sea conditions.
The current research on unmanned boats is a scientific research hotspot of modern high-end equipment manufacturing industry, but the research on group control of unmanned boat groups is still in a primary stage.
In the prior art, on one hand, in the conventional optimization algorithm, namely the particle swarm algorithm, the whale swarm algorithm and other evolutionary algorithms, the information transfer between the generations is limited to between two adjacent generations of individuals, so that the global search reference information is single, and it is difficult to explore all feasible search areas of a task sea area to obtain all target results.
On the other hand, the current control of the unmanned ship group is limited in the aspects of path planning, target detection and the like, and the navigational speed control in the navigation process of a single unmanned ship in the unmanned ship group is not involved, particularly, the sea condition in the operation sea area is not combined with the navigational speed of the unmanned ship, so that the power waste is serious in the navigation process of the unmanned ship, the maximum range cannot be reached, the detection efficiency of the unmanned ship group on the operation sea area is low, even the possibility that the operation task cannot be completed according to the plan exists, and the efficient, rapid and continuous cooperative control of the unmanned ship group is not facilitated.
Disclosure of Invention
The application aims at: when the unmanned ship group executes the multi-target operation task, the cooperative control of the unmanned ship group can be performed in real time, the navigational speed and the navigational course of the unmanned ship in the navigation process are optimized, the operation efficiency of the unmanned ship group is improved, and the reliability of the operation task is finished.
The technical scheme of the application is as follows: the unmanned ship group control method based on the African bee intelligent algorithm is suitable for controlling the unmanned ship group to execute multi-target tasks, and comprises the following steps: step 10, based on an unmanned ship group operation task and an African peak algorithm, adopting iterative operation, and determining the initial navigational speed and the predicted navigational position of the unmanned ship single ship according to the current position and the current navigational speed of the unmanned ship single ship in an operation sea area; step 20, meshing a working sea area according to a preset grid side length to generate a sea area grid, merging the sea area grids according to sea condition information in the sea area grid to generate a working task grid, and determining a task grid information matrix of the working task grid, wherein the task grid information matrix comprises grid marks and navigation speed correction amounts, and the sea condition information at least comprises wind direction, wind force and sea wave height; and 30, determining a sub-grid of the operation task grid corresponding to the predicted sailing position, determining a sailing speed correction amount according to the sub-grid to correct the initial sailing speed, generating a control instruction according to the corrected initial sailing speed and the predicted sailing position to control the unmanned ship to sail to the sub-grid, and repeatedly executing the step 10 until the unmanned ship group operation task is completed.
In any of the above technical solutions, further, the sea state information of the working sea area includes at least wind direction, wind force, and sea wave height.
In any of the above technical solutions, further, in step 2, gridding is performed on the operation sea area to generate an operation task grid, which specifically includes: step 21, dividing the grid of the operation sea area according to the preset grid side length, marking the divided grid as a first grid, and sequentially carrying out first marking on the first grid to generate a sea area grid; step 22, gridding sea state information in the sea area according to sea area grids to generate a wind direction matrix and a wind speed matrix, wherein the wind direction matrix is determined by a wind direction angle average value in a first grid, and the wind speed matrix is determined by a wind speed average value in the first grid; step 23, judging whether the difference value of the average sea wave heights in the sea area range corresponding to the adjacent sea area grids is smaller than a sea wave threshold value in sequence in a traversing mode, if so, merging the adjacent sea area grids to generate a second grid and carrying out second marking when judging that the difference value of the wind speed average value in the sea area range is smaller than the wind speed threshold value; if not, judging the next group of adjacent sea area grids until traversing is completed, wherein the second label is a set of first labels of the combined sea area grids; and step 24, generating a job task grid according to the second grid and the non-combined sea area grid, and recording the second label and the non-combined first label as grid labels.
In any of the above technical solutions, in step 2, further includes: step 25, calculating a second average value of wind direction angle average values and a second average value of wind speed average values in a corresponding sea area range in a second grid, and updating elements in a wind direction matrix and a wind speed matrix respectively according to the second average value of the wind direction angle average values and the second average value of the wind speed average values; and step 26, calculating the navigational speed correction according to the updated wind direction matrix and the updated wind speed matrix, and generating a task information matrix by combining the grid marks.
In any of the above solutions, further, step 3 further includes: step 31, judging whether the grid label of the sub-grid corresponding to the predicted navigation position is the second label, if not, determining the navigation speed correction amount corresponding to the predicted navigation position according to the grid label, correcting the initial navigation speed according to the navigation speed correction amount, and if so, executing step 32; and step 32, judging whether the grid mark of the sub-grid corresponding to the current position is the same as the grid mark of the sub-grid corresponding to the predicted navigation position, if so, setting the navigation speed correction amount corresponding to the predicted navigation position to be 0, otherwise, determining the navigation speed correction amount corresponding to the predicted navigation position according to the grid mark, and correcting the initial navigation speed.
The beneficial effects of the application are as follows:
according to the technical scheme, an African peak algorithm is combined with group control of the unmanned ship group, grid division is conducted on an operation sea area based on sea condition information in the operation sea area, so that matrix type navigational speed correction quantity is obtained, initial navigational speed of the unmanned ship single ship calculated by the African peak algorithm is corrected, the unmanned ship single ship is controlled in real time based on sea condition information in the operation sea area, navigational speed and navigational direction in the navigation process of the unmanned ship single ship are optimized, cooperative control of the unmanned ship group on sea operation is achieved, efficiency of executing the sea operation is improved, and rationality and quick response capability of unmanned ship group control are improved.
In the process of carrying out the grid division of the operation sea area, the application respectively utilizes sea condition information such as sea wave height, wind speed, wind direction and the like to form a task grid information matrix, combines the task grid information matrix with grid labels, is beneficial to improving the accuracy of the navigation speed correction, combines the divided sea area grids through sea condition information such as sea wave height, wind speed, wind direction and the like to generate a second grid, and then forms the operation task grid of the operation sea area together with the non-combined sea area grid, thereby being beneficial to reducing the occupation of operation resources in the single-boat control process of the unmanned boat and improving the real-time property of the single-boat control of the unmanned boat.
In the process of correcting the speed of the unmanned single-boat, the application also judges the value of the speed correction based on the grid marks of the divided operation task grids, if the grid numbers corresponding to the current position and the predicted sailing position are judged to be the same second mark, the sea state information representing two positions is basically the same, and at the moment, the value of the speed correction is set to 0 so as to reduce the integral calculation amount of the algorithm, improve the instantaneity, avoid frequently adjusting the output of the power device of the unmanned single-boat and reduce the complexity of the unmanned single-boat control method.
Drawings
The advantages of the foregoing and/or additional aspects of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a schematic flow diagram of an unmanned boat group control method based on an improved African bee intelligent algorithm according to one embodiment of the application;
FIG. 2 is a schematic illustration of a job task grid in accordance with one embodiment of the present application;
FIG. 3 is a schematic diagram of a modified initial velocity decomposition in accordance with an embodiment of the present application;
fig. 4 is a schematic diagram of a verification scenario in accordance with one embodiment of the present application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and the scope of the application is therefore not limited to the specific embodiments disclosed below.
As shown in fig. 1, the present embodiment provides an unmanned ship group control method based on an african bee intelligent algorithm, which is suitable for controlling the speed and the heading of each unmanned ship in an unmanned ship group by a carrier, so as to control the unmanned ship group to execute multi-target tasks and realize multi-target detection of the unmanned ship group on an operation sea area, and the method includes:
step 10, based on an unmanned ship group operation task and an African peak algorithm, adopting iterative operation, and determining the initial navigational speed and the predicted navigational position of the unmanned ship single ship according to the current position and the current navigational speed of the unmanned ship single ship in an operation sea area;
specifically, the embodiment is based on an african peak algorithm, in the algorithm, when a new global optimal solution is found in each iteration process, queen bees scatter pheromones at the global optimal solution position, a pheromone vector M is input, the residual time of the pheromones is M, the weight of the historical pheromones is gradually reduced along with the increase of iteration times, and the queen bees acquire own speed according to the historical pheromones and update the positions.
In this embodiment, each unmanned boat is used as a queen bee in the african peak algorithm (random initialization), the residual time m of the pheromone is determined according to the maximum range of the unmanned boat, and at the same time, the maximum iterative search frequency in the unmanned boat group iterative process is set to be MaxIter. The unmanned single-boat performs a search task in an operation sea area, when the current position of the unmanned single-boat is judged to have an operation target, the unmanned single-boat is regarded as finding a new global optimal solution, the current position of the unmanned single-boat is updated to the position of the queen bee, the pheromone is released, and the coordinates of the current position of the unmanned single-boat are sent to a control platform of an unmanned boat group, such as a carrier, a shore-based control platform, an airplane or an armored car.
For an unmanned single boat that is dispatched to perform a task at the jth iteration, the pheromone vector M specifically includes:
M＝[ξ Best (j)ξ Best (j+1)…ξ Best (j+m-1)] T
in xi Best (j) And (3) the corresponding global optimal solution in the j-th iteration is the historical position of the unmanned single boat.
At the time (times) of the t iteration, the current position of the kth unmanned single boat is x k (t) then upon determining the (t+1) th iteration, the kth unmanned single vessel sails to the initial voyage speed and predicted sailing position x of the next working area k (t+1), the corresponding calculation formula is:
x k (t+1)＝x k (t)+η⊙v k (t)
η＝{a 1 ，a 2 ，…a m }
a 1 ＝0.5(MaxIter-t)/MaxIter
wherein x is k (t) is the current position, v, of the kth unmanned aerial vehicle at the current iteration moment t k (t) the current navigational speed, eta.V, of the kth unmanned aerial vehicle at the current iteration moment t k (t) voyage to next operation for kth unmanned single boatInitial navigational speed of area, a 2 、a 3 、…、a m-1 Is a as 1 ～a m To achieve the purpose of reducing the weight of the historical pheromone with the increase of time by taking i as an intermediate parameter and rand i(t) For the ith random number obeying uniform distribution in the (0, 1) interval at the current moment t, maxIter is the maximum iteration number, and xi Best () Is a globally optimal solution.
Step 20, meshing the operation sea area according to the preset grid side length to generate a sea area grid, merging the sea area grids according to sea condition information in the sea area grid to generate an operation task grid, and determining a task grid information matrix of the operation task grid, wherein the task grid information matrix comprises grid marks and a navigation speed correction amount, and the sea condition information at least comprises wind direction, wind force and sea wave height;
in this embodiment, the carrier can obtain sea state information of the operating sea area, including at least information of wind direction, wind force, sea wave height, and the like, where such information can be obtained by existing weather detection equipment, such as weather stations, automatic ship identification systems AIS, millimeter wave radars, lidars, and the like.
After sea state information is acquired, the processing such as coordinate system conversion, gridding, time scale calibration, motion prediction and the like is carried out so as to improve the accuracy of a task grid information matrix.
Step 21, dividing the grid of the operation sea area according to the preset grid side length, marking the divided grid as a first grid, sequentially carrying out first marking on the first grid to generate a sea area grid, and determining a sea area range corresponding to the first grid;
specifically, when meshing a working sea area and determining a task grid information matrix, firstly presetting a grid side length, dividing the working sea area into alpha multiplied by beta grids, recording the alpha multiplied by beta grids as a first grid, sequentially carrying out first marks on the first grid to generate a sea area grid, and determining a sea area range corresponding to the first grid based on coordinates in the working sea area range.
Thus, the generated sea area grid is formed by splicing a plurality of first grids, corresponding to the whole operation sea area, and each first grid corresponds to a certain area in the operation sea area.
Based on the sea area meshing, the meshing of sea state information can be realized by calculating the average value of the wind speed, the wind direction and the sea wave height in the area, the sea state information and the sea area meshing are in one-to-one correspondence, so that the initial navigational speed of the unmanned ship single boat is corrected based on the sea state information, the cooperative control of the unmanned ship group is carried out in real time, and the navigational speed and the navigational course of the unmanned ship in the navigation process are optimized.
Step 22, gridding sea state information in the sea area according to the sea area grids to generate a wind direction matrix theta and a wind speed matrix v wind The wind direction matrix θ is determined by the mean value of the wind direction angles in the first grid, and the wind speed matrix v wind The wind speed average value in the first grid is determined, and the corresponding matrix formula is as follows:
in the wind direction angle average value theta ab The value of the wind speed average value v is a first average value of wind direction angles in the sea area range corresponding to the a-th row and the b-th column of the first grid ab The values of a row a and b are the first average value of wind speeds in the sea area range corresponding to the first grid, a=1, 2.
In order to reduce the occupation of operation resources in the single-boat control process of the unmanned boat and improve the real-time performance of the single-boat control of the unmanned boat, the method for merging the grids in the sea area specifically comprises the following steps:
step 23, judging whether the difference value of the average sea wave heights in the sea area range corresponding to the adjacent sea area grids is smaller than a sea wave threshold value in sequence in a traversing mode, if so, merging the adjacent sea area grids to generate a second grid and carrying out second marking when judging that the difference value of the wind speed average value in the sea area range is smaller than the wind speed threshold value; if not, judging the next group of adjacent sea area grids until traversing is completed, wherein the second label is a set of first labels of the combined sea area grids;
step 24, generating a job task grid according to the second grid and the non-combined sea area grid, and marking the second mark and the non-combined first mark as grid marks;
as shown in fig. 2, taking a local sea grid as an example, the embodiment uses an eight-connected-area traversal mode to merge the sea grids. The sea area mesh 33 is traversed, and the eight connected areas corresponding to the sea area mesh are the sea area mesh 22, the sea area mesh 23, the sea area mesh 24, the sea area mesh 32, the sea area mesh 34, the sea area mesh 42, the sea area mesh 43 and the sea area mesh 44.
And sequentially calculating the difference value between the average sea wave height in the sea area range corresponding to the 8 sea area grids and the average sea wave height corresponding to the sea area grid 33, sequentially comparing the difference value with a set sea wave threshold value, and if the difference value corresponding to the sea area grid 24, the sea area grid 34, the sea area grid 42, the sea area grid 43 and the sea area grid 44 is smaller than the set sea wave threshold value, calculating the difference value between the average wind speed value in the sea area range corresponding to the 5 sea area grids and the average wind speed value corresponding to the sea area grid 33, sequentially comparing the difference value with the set wind speed threshold value, and if the difference value corresponding to the sea area grid 34, the sea area grid 43 and the sea area grid 44 is smaller than the set wind speed threshold value, considering that the sea area grid 34, the sea area grid 43 and the sea area grid 44 can be combined with the sea area grid 33.
In addition, since the traversal is adopted, the finally generated second grid may be shown by a dotted line in fig. 2, and in this case, the second reference numerals of the second grid are {33, 34, 43, 44, 45, 53, 54, 55}.
Step 25, calculating a second average value of the wind direction angle average values and a second average value of the wind speed average values in the corresponding sea area range in the second grid, and respectively aiming at the wind direction matrix theta and the wind speed matrix v according to the second average value of the wind direction angle average values and the second average value of the wind speed average values wind Updating the elements in the file;
specifically, when a certain second grid is {33, 34, 43, 44, 45, 53, 54, 55} to be calculated, performing matrix updating to obtain a second average value of wind speeds and wind angles in the grid, and setting the corresponding row and column element value as the second average value, namely, the second average value of row elements 33, 34, 43, 44, 45, 53, 54, 55 in the wind direction matrix θ is the second average value of wind directions angles, and the wind speed matrix v wind The values in the row and column elements 33, 34, 43, 44, 45, 53, 54, 55 are the second average of the wind speed.
Step 26, according to the updated wind direction matrix theta and wind speed matrix v wind Calculating a navigational speed correction quantity Deltax, and combining grid marks to generate a task information matrix, wherein a calculation formula corresponding to the navigational speed correction quantity Deltav is as follows:
specifically, as shown in fig. 3, when a certain unmanned ship sails to a certain sub-grid in the task grid, the sub-grid is an uncombined sea area grid or one sea area grid in the combined second grid, and eight navigation speed correction areas can be divided by taking the sea area plane of the unmanned ship as a direction range every 45 degrees, so that a calculation formula corresponding to the navigation speed correction amount is set as shown in the formula. And then the calculated navigational speed correction quantity and the grid marks are in one-to-one correspondence, so that a task information matrix can be generated.
Step 30, determining a sub-grid of the operation task grid corresponding to the predicted sailing position, determining a sailing speed correction amount according to the sub-grid to correct the initial sailing speed, generating a control instruction according to the corrected initial sailing speed and the predicted sailing position to control the unmanned ship to sail to the sub-grid, and repeatedly executing step 10 until the unmanned ship group operation task is completed, wherein the initial sailing speed can be corrected based on the sailing speed correction amount by adopting sum operation.
Specifically, after the predicted sailing position is determined, the position corresponds to a coordinate in the operation sea area, because each area in the operation sea area corresponds to a sub-grid in the operation task grid, according to the grid label of the sub-grid, the sailing speed correction amount in the task grid information matrix can be determined in a query mode, so that the predicted attempt is corrected, and the sailing speed of the unmanned single boat is controlled according to sea state information in real time.
In addition, in the African peak algorithm, when the unmanned single-boat sails to the expected sailing position according to the corrected expected sailing speed, because the current sailing speed is the initial sailing speed in the last iteration after correction, the course of the unmanned single-boat is corrected in real time based on sea state information in the iteration process, so that the real-time control of the unmanned single-boat is optimized, and the operation efficiency of the unmanned single-boat group and the reliability of completing the operation task can be improved.
Furthermore, in order to reduce the calculation amount of the algorithm and improve the real-time performance, before the initial navigational speed is corrected in the step 3, the method further comprises:
step 31, judging whether the grid label of the sub-grid corresponding to the predicted navigation position is the second label, if not, determining the navigation speed correction amount corresponding to the predicted navigation position according to the grid label, correcting the initial navigation speed according to the navigation speed correction amount, and if so, executing step 32;
and step 32, judging whether the grid mark of the sub-grid corresponding to the current position is the same as the grid mark of the sub-grid corresponding to the predicted navigation position, if so, setting the navigation speed correction amount corresponding to the predicted navigation position to be 0, otherwise, determining the navigation speed correction amount corresponding to the predicted navigation position according to the grid mark, and correcting the initial navigation speed.
Specifically, when the grid number of the sub-grid where the unmanned ship is currently located is the second number, the second grid corresponding to the second number is formed by combining a plurality of sea area grids, and the sea state information of the combined sea area grids is basically the same. Therefore, in order to ensure the real-time performance and continuity of the control of the unmanned single-boat, the output of a power device of the unmanned single-boat is prevented from being frequently regulated, the situation that the predicted navigation position and the current position belong to the same second grid in the next iteration process is avoided, the initial navigation speed calculated according to the African peak algorithm is not corrected, and the complexity of the unmanned single-boat control method is reduced.
In this embodiment, a certain second grid is set to be formed by combining a sea area grid 33, a sea area grid 34, a sea area grid 43, a sea area grid 44, a sea area grid 45, a sea area grid 53, a sea area grid 54, a sea area grid 55 and the like, a sub-grid corresponding to the current position of a certain unmanned ship single boat belongs to the second grid, and the corresponding grid reference number is set to be 43.
When the grid mark of the sub-grid corresponding to the predicted navigation position is 42, and the grid mark 42 does not belong to the second grid, correcting the initial navigation speed according to the navigation speed correction amount corresponding to the grid mark 42;
when the grid number of the sub-grid corresponding to the predicted navigation position is 44, and the sub-grid 44 belongs to the second grid, the navigation speed correction amount is set to 0, and the initial navigation speed is not corrected, so that the complexity of the unmanned single-boat control method is reduced.
In this embodiment, in order to verify the above method, a verification environment is set as shown in fig. 4, a predetermined sea area range of 100 square seawall rectangle travelled by A, B, C, D is set, buoys are arranged in advance at the longitude and latitude positions of A, B, C, D respectively, and ■, < > and @ respectively represent virtual target schematic representations of color buoys, floating wooden piles, metal balls and the like which are arranged in advance. Algorithm parameter m=3, a m ＝1，δ 1 ＝1.3，δ 2 The scale of the boat group is N=5, the maximum iteration number is MaxIter=50, the unmanned boat parameter is 19m long, the water discharge is 40t, the highest voyage speed is 38 knots (70.4 km/h), the endurance is 48 hours, and the voyage distance is 1260km. And executing a task process, wherein the boat group transits to a task area at the speed of 38 knots of the highest navigational speed, and the searching process carries out intelligent searching at the cruising speed of 6 knots.
The sea state information of the unmanned ship group operation sea area is four-level sea state, the wave height is 1.25-2.5 m, the wind speed is small, the visibility is good, the number of false targets is 10, the longitude and latitude of the position of the false target are recorded in real time, and after 9 iterations, the searching and positioning of all targets are completed in about 2 hours.
In order to ensure that the unmanned boat group can successfully execute the detection task, before executing the detection task, the method further comprises the following steps:
and carrying out communication test on each unmanned ship in the unmanned ship group, entering a task interruption state when the communication feedback signal of the unmanned ship is not received in a preset time period or when the communication fault signal of the unmanned ship is received in the preset time period, sending standby instructions to a plurality of unmanned ships, and carrying out communication self-test so as to facilitate maintenance of a communication system by an operator.
Specifically, the communication test message can be sent to each unmanned ship through the remote control module to carry out communication test, if the communication system of each unmanned ship can normally operate, the communication module in the unmanned ship feeds back a communication normal state response signal to the remote control module, and at the moment, the remote control module records that the unmanned ship is in a task ready state, and a detection task is executed.
If communication abnormality occurs in the unmanned ship, namely the remote control module cannot receive a communication feedback signal fed back by the unmanned ship communication module in preset time or receives a communication fault signal, the remote control module records that the unmanned ship enters a task interruption state, meanwhile, communication self-test is carried out, an operator overhauls a communication system, and after the fault is removed, communication test is carried out again until all unmanned ships enter a task ready state.
When the unmanned ship group completes the communication test and enters a task ready state, a remote control module sends a control instruction to each unmanned ship according to the unmanned ship group control method based on the improved African bee intelligent algorithm in the embodiment so as to perform target detection on the operation sea area.
The technical scheme of the application is explained in detail with reference to the accompanying drawings, and the application provides an unmanned boat group control method based on an African bee intelligent algorithm, which comprises the following steps: step 10, based on an unmanned ship group operation task and an African peak algorithm, adopting iterative operation, and determining the initial navigational speed and the predicted navigational position of the unmanned ship single ship according to the current position and the current navigational speed of the unmanned ship single ship in an operation sea area; step 20, meshing the operation sea area according to sea state information of the operation sea area, generating operation task grids, and determining a task grid information matrix of the operation task grids, wherein the task grid information matrix comprises grid marks and navigational speed correction amounts; and 30, determining a sub-grid of the operation task grid corresponding to the predicted sailing position, determining a sailing speed correction amount according to the sub-grid to correct the initial sailing speed, generating a control instruction according to the corrected initial sailing speed and the predicted sailing position to control the unmanned ship to sail to the sub-grid, and repeatedly executing the step 10 until the unmanned ship group operation task is completed. According to the technical scheme, when the unmanned ship group executes the multi-target operation task, the cooperative control of the unmanned ship group can be performed in real time, the navigational speed and the navigational course of the unmanned ship in the navigation process are optimized, and the operation efficiency of the unmanned ship group and the reliability of completing the operation task are improved.
The steps in the application can be sequentially adjusted, combined and deleted according to actual requirements.
The units in the device can be combined, divided and deleted according to actual requirements.
Although the application has been disclosed in detail with reference to the accompanying drawings, it is to be understood that such description is merely illustrative and is not intended to limit the application of the application. The scope of the application is defined by the appended claims and may include various modifications, alterations and equivalents of the application without departing from the scope and spirit of the application.
Claims (2)
1. An unmanned boat group control method based on an african bee intelligent algorithm, which is suitable for controlling the unmanned boat group to execute multi-target tasks, and is characterized by comprising the following steps:
step 10, based on an unmanned ship group operation task and an African peak algorithm, adopting iterative operation, and determining the initial navigational speed and the predicted navigational position of the unmanned ship single ship according to the current position and the current navigational speed of the unmanned ship single ship in an operation sea area;
step 20, meshing the operation sea area according to a preset grid side length to generate a sea area grid, merging the sea area grids according to sea state information in the sea area grid to generate an operation task grid, and determining a task grid information matrix of the operation task grid, wherein the task grid information matrix comprises grid marks and a navigation speed correction amount, and the sea state information at least comprises wind direction, wind power and sea wave height;
step 30, determining a sub-grid of a work task grid corresponding to the predicted sailing position, determining the sailing speed correction amount according to the sub-grid to correct the initial sailing speed, generating a control instruction according to the corrected initial sailing speed and the predicted sailing position to control the unmanned boat to sail to the sub-grid, and repeatedly executing step 10 until the unmanned boat group work task is completed;
in the step 20, generating a job task grid specifically includes:
step 21, according to the preset grid side length, carrying out grid division on the operation sea area, marking the divided grid as a first grid, and sequentially carrying out first marking on the first grid to generate the sea area grid;
step 22, gridding sea state information in the sea area range according to the sea area grids to generate a wind direction matrix and a wind speed matrix, wherein the wind direction matrix is determined by a wind direction angle average value in the first grid, and the wind speed matrix is determined by a wind speed average value in the first grid;
step 23, judging whether the difference value of the average sea wave heights in the sea area range corresponding to the adjacent sea area grids is smaller than a sea wave threshold value in sequence in a traversing mode, if so, merging the adjacent sea area grids to generate a second grid, and carrying out second marking when judging that the difference value of the average wind speed values in the sea area range is smaller than the wind speed threshold value; if not, judging the next group of adjacent sea area grids until traversing is completed, wherein the second label is a set of first labels of the combined sea area grids;
step 24, generating the operation task grid according to the second grid and the uncombined sea area grid, and marking the second mark and the uncombined first mark as the grid marks;
in the step 20, further includes:
step 25, calculating a second average value of wind direction angle average values and a second average value of wind speed average values in the corresponding sea area range in the second grid, and updating elements in the wind direction matrix and the wind speed matrix respectively according to the second average value of the wind direction angle average values and the second average value of the wind speed average values;
and step 26, calculating the navigational speed correction according to the updated wind direction matrix and the updated wind speed matrix, and generating the task grid information matrix by combining the grid marks.
2. The unmanned yacht group control method based on the african bee intelligent algorithm as claimed in claim 1, wherein the step 30 further comprises:
step 31, judging whether the grid label of the sub-grid corresponding to the predicted navigation position is a second label, if not, determining a navigation speed correction amount corresponding to the predicted navigation position according to the grid label, correcting the initial navigation speed according to the navigation speed correction amount, and if so, executing step 32;
and step 32, judging whether the grid number of the sub-grid corresponding to the current position is the same as the grid number of the sub-grid corresponding to the predicted navigation position, if so, setting the navigation speed correction amount corresponding to the predicted navigation position to be 0, otherwise, determining the navigation speed correction amount corresponding to the predicted navigation position according to the grid number, and correcting the initial navigation speed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110722765.6A CN113655786B (en) | 2021-06-29 | 2021-06-29 | Unmanned boat group control method based on African bee intelligent algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110722765.6A CN113655786B (en) | 2021-06-29 | 2021-06-29 | Unmanned boat group control method based on African bee intelligent algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113655786A CN113655786A (en) | 2021-11-16 |
| CN113655786B true CN113655786B (en) | 2023-09-19 |
Family
ID=78477115
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110722765.6A Active CN113655786B (en) | 2021-06-29 | 2021-06-29 | Unmanned boat group control method based on African bee intelligent algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113655786B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102175245A (en) * | 2011-01-28 | 2011-09-07 | 哈尔滨工程大学 | Underwater vehicle path planning method based on ocean current historical statistic information |
| KR20190077966A (en) * | 2017-12-26 | 2019-07-04 | 동강엠텍(주) | Optimal route inference device for ship |
| CN110083983A (en) * | 2019-05-17 | 2019-08-02 | 大连海事大学 | A kind of boat segmental speed of a ship or plane optimization method and intelligent management system |
| CN111060109A (en) * | 2020-01-03 | 2020-04-24 | 东南大学 | Unmanned ship global path planning method based on improved A-star algorithm |
| CN111222701A (en) * | 2020-01-08 | 2020-06-02 | 中国船舶重工集团公司第七二四研究所 | Marine environment map layer-based automatic planning and evaluation method for ship route |
| CN112068564A (en) * | 2020-09-10 | 2020-12-11 | 中国船舶科学研究中心 | Intelligent ship control method based on economic navigation optimization |
| CN112435505A (en) * | 2020-11-11 | 2021-03-02 | 南通中远海运川崎船舶工程有限公司 | Autonomous navigation system based on optimal navigation speed and navigation method thereof |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20210046500A (en) * | 2019-10-18 | 2021-04-28 | 한국전자통신연구원 | Apparatus and Method for Automatic Sailing of Ship and Recording Medium |
-
2021
- 2021-06-29 CN CN202110722765.6A patent/CN113655786B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102175245A (en) * | 2011-01-28 | 2011-09-07 | 哈尔滨工程大学 | Underwater vehicle path planning method based on ocean current historical statistic information |
| KR20190077966A (en) * | 2017-12-26 | 2019-07-04 | 동강엠텍(주) | Optimal route inference device for ship |
| CN110083983A (en) * | 2019-05-17 | 2019-08-02 | 大连海事大学 | A kind of boat segmental speed of a ship or plane optimization method and intelligent management system |
| CN111060109A (en) * | 2020-01-03 | 2020-04-24 | 东南大学 | Unmanned ship global path planning method based on improved A-star algorithm |
| CN111222701A (en) * | 2020-01-08 | 2020-06-02 | 中国船舶重工集团公司第七二四研究所 | Marine environment map layer-based automatic planning and evaluation method for ship route |
| CN112068564A (en) * | 2020-09-10 | 2020-12-11 | 中国船舶科学研究中心 | Intelligent ship control method based on economic navigation optimization |
| CN112435505A (en) * | 2020-11-11 | 2021-03-02 | 南通中远海运川崎船舶工程有限公司 | Autonomous navigation system based on optimal navigation speed and navigation method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113655786A (en) | 2021-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111157982A (en) | Intelligent ship and shore cooperative target tracking system and method based on shore-based radar | |
| CN110244720B (en) | Path planning method and system for unmanned sea boat | |
| CN113342008B (en) | Path planning system and method for sea-air cooperative underwater target tracking | |
| CN111913481B (en) | Multi-unmanned-ship cooperative formation method with variable pilot modes | |
| CN110956853A (en) | Multi-ship collision prediction method, system and storage medium | |
| CN113093733B (en) | Sea-to-sea striking method for unmanned boat cluster | |
| CN111898285A (en) | Underwater unmanned autonomous vehicle cluster operation efficiency evaluation method | |
| CN115824217A (en) | Maritime search and rescue method and system | |
| CN111538349B (en) | Long-range AUV autonomous decision-making method oriented to multiple tasks | |
| CN110333723B (en) | Unmanned ship collaborative formation method based on dual communication equipment | |
| CN116578095A (en) | Energy-saving obstacle avoidance method for ocean energy driven robot | |
| CN115018304B (en) | Method and device for calculating collision risk of ship computer and storage medium | |
| CN114088094A (en) | Intelligent route planning method and system for unmanned ship | |
| Lun et al. | Target search in dynamic environments with multiple solar-powered UAVs | |
| CN113655786B (en) | Unmanned boat group control method based on African bee intelligent algorithm | |
| Yang et al. | Multi agents to search and rescue based on group intelligent algorithm and edge computing | |
| CN113359796A (en) | Unmanned aerial vehicle searching method for underground multi-branch cave | |
| CN116859928A (en) | Cluster target tracking method based on navigator self-adaption | |
| CN115718905A (en) | VTS system-oriented multi-sensor information fusion method | |
| CN114943168A (en) | Overwater floating bridge combination method and system | |
| Zheng et al. | Inland river ship auxiliary collision avoidance system | |
| Kontzinos et al. | STATE-OF-THE-ART ANALYSIS OF ARTIFICIAL INTELLIGENCE APPROACHES IN THE MARITIME INDUSTRY | |
| CN113655785B (en) | Unmanned ship group control method based on hybrid algorithm | |
| CN112330091B (en) | Satellite-borne SAR imaging autonomous task planning method | |
| CN117173934B (en) | Marine threat target interception point forecasting method and system for unmanned ship cluster convoy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |